© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34540
    Prev
    Next
    INDEX
    Explanations

    options that are

    np_acts-logits-general · gemini-2.5-flash-lite

    the main thing this neuron does is find first-person personal narrative text (pronoun “I” and associated personal experience verbs)

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     or
    -1.19
     their
    -1.13
    ДА
    -1.10
     EconPapers
    -1.03
     of
    -0.96
     using
    -0.93
    我们
    -0.90
     osobow
    -0.90
     рекоменду
    -0.88
    本
    -0.88
    POSITIVE LOGITS
     gainera
    1.34
     aço
    1.34
     healthy
    1.23
     enjoy
    1.17
     enough
    1.15
     cremallera
    1.14
     nice
    1.13
     wonderful
    1.13
     freedom
    1.13
     frumo
    1.12
    Activations Density 0.062%

    No Known Activations